Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 91 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2927. Min Act: -0.0001

Data Index: 47862 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2622. Min Act: -0.0001

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2518. Min Act: -0.0000

Data Index: 989087 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1153466 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2561. Min Act: -0.0001

Data Index: 346515 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2644. Min Act: -0.0000

Data Index: 101364 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2605. Min Act: -0.0001

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2495. Min Act: -0.0001

Data Index: 837565 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2376. Min Act: -0.0000

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2355. Min Act: -0.0000

Data Index: 873857 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2458. Min Act: -0.0001

Data Index: 171793 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2443. Min Act: -0.0001

Data Index: 409170 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2379. Min Act: -0.0001

Data Index: 253332 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2369. Min Act: -0.0001

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2346. Min Act: -0.0001

Data Index: 647548 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2251. Min Act: -0.0001

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2246. Min Act: -0.0000

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2328. Min Act: -0.0000

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2332. Min Act: -0.0001

Data Index: 814568 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.2927. Min Range: -0.2927

Max Act: 0.2246. Min Act: -0.0001

Data Index: 829765 (C4 (Web Text))

Max Activating Token Index: 78